Commit 9de76f55 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'gro-inline-tcp6_gro_-receive-complete' 

Eric Dumazet says:

====================
gro: inline tcp6_gro_{receive,complete}

On some platforms, GRO stack is too deep and causes cpu stalls.

Decreasing call depths by one shows a 1.5 % gain on Zen2 cpus.
(32 RX queues, 100Gbit NIC, RFS enabled, tcp_rr with 128 threads and 10,000 flows)

We can go further by inlining ipv6_gro_{receive,complete}
and take care of IPv4 if there is interest.

Note: two temporary __always_inline will be replaced with
      inline_for_performance when/if available.

Cumulative size increase for this series (of 3):

$ scripts/bloat-o-meter -t vmlinux.0 vmlinux.3
add/remove: 2/2 grow/shrink: 5/1 up/down: 1572/-471 (1101)
Function                                     old     new   delta
ipv6_gro_receive                            1069    1846    +777
ipv6_gro_complete                            433     733    +300
tcp6_check_fraglist_gro                        -     272    +272
tcp6_gro_complete                            227     306     +79
tcp4_gro_complete                            325     397     +72
ipv6_offload_init                            218     274     +56
__pfx_tcp6_check_fraglist_gro                  -      16     +16
__pfx___skb_incr_checksum_unnecessary         32       -     -32
__skb_incr_checksum_unnecessary              186       -    -186
tcp6_gro_receive                             959     706    -253
Total: Before=22592724, After=22593825, chg +0.00%
====================

Link: https://patch.msgid.link/20260120164903.1912995-1-edumazet@google.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents a4674aa5 b8d9b7da

include/linux/skbuff.h

+1 −1
Original line number Diff line number Diff line
@@ -4763,7 +4763,7 @@ static inline void __skb_decr_checksum_unnecessary(struct sk_buff *skb) 
	}

}



static inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)

static __always_inline void __skb_incr_checksum_unnecessary(struct sk_buff *skb)

{

	if (skb->ip_summed == CHECKSUM_UNNECESSARY) {

		if (skb->csum_level < SKB_MAX_CSUM_LEVEL)

include/net/gro.h

+2 −3
Original line number Diff line number Diff line
@@ -405,9 +405,8 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, 
							   struct sk_buff *));

INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));



INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,

							   struct sk_buff *));

INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));

struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *);

int udp6_gro_complete(struct sk_buff *, int);



#define indirect_call_gro_receive_inet(cb, f2, f1, head, skb)	\

({								\

include/net/tcp.h

+0 −2
Original line number Diff line number Diff line
@@ -2324,8 +2324,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, 
				struct tcphdr *th);

INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));

INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));

INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));

INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb));

#ifdef CONFIG_INET

void tcp_gro_complete(struct sk_buff *skb);

#else

net/ipv6/Makefile

+1 −1
Original line number Diff line number Diff line
@@ -45,7 +45,7 @@ obj-$(CONFIG_IPV6_FOU) += fou6.o 


obj-y += addrconf_core.o exthdrs_core.o ip6_checksum.o ip6_icmp.o

obj-$(CONFIG_INET) += output_core.o protocol.o \

			ip6_offload.o tcpv6_offload.o exthdrs_offload.o

			ip6_offload.o exthdrs_offload.o



obj-$(subst m,y,$(CONFIG_IPV6)) += inet6_hashtables.o

net/ipv6/ip6_offload.c

+22 −21
Original line number Diff line number Diff line
@@ -19,23 +19,7 @@ 
#include <net/gso.h>



#include "ip6_offload.h"



/* All GRO functions are always builtin, except UDP over ipv6, which lays in

 * ipv6 module, as it depends on UDPv6 lookup function, so we need special care

 * when ipv6 is built as a module

 */

#if IS_BUILTIN(CONFIG_IPV6)

#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_2(f, f2, f1, __VA_ARGS__)

#else

#define INDIRECT_CALL_L4(f, f2, f1, ...) INDIRECT_CALL_1(f, f2, __VA_ARGS__)

#endif



#define indirect_call_gro_receive_l4(f2, f1, cb, head, skb)	\

({								\

	unlikely(gro_recursion_inc_test(skb)) ?			\

		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\

		INDIRECT_CALL_L4(cb, f2, f1, head, skb);	\

})

#include "tcpv6_offload.c"



static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)

{
@@ -298,9 +282,19 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head, 


	skb_gro_postpull_rcsum(skb, iph, nlen);



	pp = indirect_call_gro_receive_l4(tcp6_gro_receive, udp6_gro_receive,

					 ops->callbacks.gro_receive, head, skb);

	if (unlikely(gro_recursion_inc_test(skb))) {

		flush = 1;

		goto out;

	}



	if (likely(proto == IPPROTO_TCP))

		pp = tcp6_gro_receive(head, skb);

#if IS_BUILTIN(CONFIG_IPV6)

	else if (likely(proto == IPPROTO_UDP))

		pp = udp6_gro_receive(head, skb);

#endif

	else

		pp = ops->callbacks.gro_receive(head, skb);

out:

	skb_gro_flush_final(skb, pp, flush);
@@ -379,11 +373,18 @@ INDIRECT_CALLABLE_SCOPE int ipv6_gro_complete(struct sk_buff *skb, int nhoff) 
	}



	nhoff += sizeof(*iph) + ipv6_exthdrs_len(iph, &ops);



	if (likely(ops == &net_hotdata.tcpv6_offload))

		return tcp6_gro_complete(skb, nhoff);

#if IS_BUILTIN(CONFIG_IPV6)

	if (ops == &net_hotdata.udpv6_offload)

		return udp6_gro_complete(skb, nhoff);

#endif



	if (WARN_ON(!ops || !ops->callbacks.gro_complete))

		goto out;



	err = INDIRECT_CALL_L4(ops->callbacks.gro_complete, tcp6_gro_complete,

			       udp6_gro_complete, skb, nhoff);

	err = ops->callbacks.gro_complete(skb, nhoff);



out:

	return err;